claude-poc

There are multiple ways to abuse Claude code, this is one of them which I found during my research & reported November 23, 2025 not-fixed, might come handy while doing RT/PT for inital access. Summary: The apiKeyHelper is a custom shell script /bin/sh designed to generate authentication values fo...

MMSkillRisk

Guizang Social Card Skill · Xiaohongshu Carousels / WeChat Cover Pairs 中文 README An agent skill for Claude Code, Codex, and similar coding-agent environments. It generates Xiaohongshu / Rednote carousel images , Live Photo motion cards , and WeChat 21:9 + 1:1 cover pairs from articles, copy,...

CVE-2026-86063

A flaw was found in Claude Code. When installing a plugin pinned to a specific commit hash, the application does not verify that the checked-out version matches the expected Secure Hash Algorithm SHA identifier. A remote attacker controlling a repository can create a branch named after the review...

CVE-2026-86063

Claude Code is an agentic coding tool. Prior to 2.1.179, the Claude Code and Claude Desktop plugin installation flow runs git checkout for a marketplace-pinned commit without verifying that the resulting HEAD equals the pinned 40-character SHA. An attacker who controls a plugin repository on a Gi...

CVE-2026-86063

The agentic coding tool Claude Code (and the Claude Desktop plugin) is vulnerable to a plugin hash pinning bypass prior to version 2.1.179 . The flaw exists because the installation flow executes git checkout for a marketplace-pinned commit without verifying that the resulting HEAD matches the ex...

CVE-2026-86063 Claude Code: Plugin Hash Pin Bypass Allows Bypass of Hash Pinning

Claude Code is an agentic coding tool. Prior to 2.1.179, the Claude Code and Claude Desktop plugin installation flow runs git checkout for a marketplace-pinned commit without verifying that the resulting HEAD equals the pinned 40-character SHA. An attacker who controls a plugin repository on a Gi...

PT-2026-112875

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.1.179 Description The plugin installation flow for Claude Code and Claude Desktop executes a git checkout for a marketplace-pinned commit but fails to verify if the resulting HEAD matches the pinned 40-character...

firmware-reverse-engineering

Firmware Reverse Engineering Skills Five agent skills from OrbitCurve for firmware extraction, static analysis, Ghidra reverse engineering, emulation, and security reporting, by Hussein Muhaisen. The collection packages the existing workflows, references, templates, and Ghidra scripts for Claude...

security-harness

Security Harness A multi-agent application-security review harness for Claude Code and, later, other AI agents. One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies...

shai-hulud-scan

shai-hulud-scan A Claude Code skill that scans machines for indicators of compromise IOCs from the Mini Shai-Hulud supply chain worm CVE-2026-45321, CVSS 9.6. What is Mini Shai-Hulud? A self-propagating supply chain worm that compromised 170+ npm/PyPI packages on May 11, 2026 - including...

CyberXero Uses Claude Code in Campaign That Stole Over 628,000 Ukrainian Records

Cybersecurity researchers have disclosed details of a two-pronged artificial intelligence AI-augmented initial access campaign targeting WordPress sites, e-commerce platforms, and critical infrastructure entities in Ukraine. The activity, which brings together commodity offensive tools like Cobal...

ai-tool-poisoning-guard

ai-tool-poisoning-guard Minimum security-baseline rule for Claude Code, Codex, and Cursor. This free rule closes a real gap in each tool's built-in review. Full ruleset + implementation guide: Gumroad link — coming soon. Your AI coding assistant reviews code. It doesn't review the sentence that...

lowkey

Agentes de Codificación de IA Auto-Alojados en AWS — OpenClaw, Claude Code, Codex, Kiro, NemoClaw, Hermes ▶️ Mira el tutorial completo en YouTube 📝 Lee el artículo del blog: "Le di a mi agente su propia cuenta de AWS" TL;DR — despliega Lowkey: curl -sfL install.lowkey.run | bash Funciona en bash ,...

claude-bug-bounty

AI-powered bug bounty hunting — recon to report, in your terminal. What Is This · Trusted By · Free Setup · Quick Start · Commands · What It Finds · AXguard · Support · FAQ Built and maintained by AwareXone · Website · X · GitHub !SocialSafe by AwareXone provides case review and assistance for...

claude-code-devcontainer

Claude Code in un devcontainer Un ambiente di sviluppo sandbox per eseguire Claude Code con bypassPermissions abilitato in sicurezza. Realizzato presso Trail of Bits per flussi di lavoro di audit di sicurezza. Perché usarlo? Eseguire Claude con bypassPermissions sulla tua macchina host è rischios...

raptor

╔═══════════════════════════════════════════════════════════════════════════╗ ║ ║ ║ ██████╗ █████╗ ██████╗ ████████╗ ██████╗ ██████╗ ║ ║ ██╔══██╗██╔══██╗██╔══██╗╚══██╔══╝██╔═══██╗██╔══██╗ ║ ║ ██████╔╝███████║██████╔╝ ██║ ██║ ██║██████╔╝ ║ ║ ██╔══██╗██╔══██║██╔═══╝ ██║ ██║ ██║██╔══██╗ ║ ║ ██║ ██║█...

CVE-2026-103435

A flaw was found in claude-code. An attacker with write access to a shared workspace can achieve arbitrary file modification and privilege escalation by exploiting a time-of-check to time-of-use TOCTOU race condition. By replacing a project file with a symbolic link between the permission check a...

CVE-2026-103435

Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that validation. This time-of-check to time-of-use TOCTOU gap allowed an attacker who could write to the workspace to...

CVE-2026-103435 Arbitrary File Write via Write-Time Symlink Following (TOCTOU) in Claude Code

Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that validation. This time-of-check to time-of-use TOCTOU gap allowed an attacker who could write to the workspace to...

CVE-2026-103435 Arbitrary File Write via Write-Time Symlink Following (TOCTOU) in Claude Code

Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that validation. This time-of-check to time-of-use TOCTOU gap allowed an attacker who could write to the workspace to...